Skip to content

Conversation

@AAdIprog
Copy link

Description

Resolves #95

This PR adds a dedicated installation guide for Kernel-Native Mode to the quick-start.md documentation.

Changes

  • Refactored the "Install Kmesh" section to use Tabs, clearly separating instructions for:
    • Dual Engine (Default)
    • Kernel Native
  • Added specific steps for Kernel-Native mode, including:
    • Prerequisite check for Enhanced Kernel.
    • Instructions to modify values.yaml (via sed) or Yaml config to enable kernel-native mode before installation.
  • Ensured the "Verify Installation" section remains accessible for both modes.

Verification

  • Built the documentation locally and verified the Tab functionality.
  • Confirmed that "Kernel Native" specific instructions (like setting --mode=kernel-native) are correct and easy to follow.

Copilot AI review requested due to automatic review settings January 11, 2026 10:16
@netlify
Copy link

netlify bot commented Jan 11, 2026

Deploy Preview for kmesh-net ready!

Name Link
🔨 Latest commit 956a9e9
🔍 Latest deploy log https://app.netlify.com/projects/kmesh-net/deploys/6963788c6e00410008865f92
😎 Deploy Preview https://deploy-preview-268--kmesh-net.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify project configuration.

@kmesh-bot
Copy link
Collaborator

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign kevin-wangzefeng for approval. For more information see the Kubernetes Code Review Process.

The full list of commands accepted by this bot can be found here.

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@kmesh-bot
Copy link
Collaborator

Welcome @AAdIprog! It looks like this is your first PR to kmesh-net/website 🎉

@gemini-code-assist
Copy link

Summary of Changes

Hello @AAdIprog, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the Kmesh quick-start documentation by introducing a structured and user-friendly guide for installing Kmesh in Kernel-Native mode. By organizing installation instructions into tabbed sections for both Dual Engine and Kernel-Native modes, the changes aim to provide a clearer and more intuitive path for users to set up Kmesh according to their specific operational requirements, ultimately improving the overall clarity and usability of the documentation.

Highlights

  • Kernel-Native Mode Installation Guide: Added a dedicated and comprehensive installation guide for Kmesh's Kernel-Native Mode to the quick-start documentation.
  • Tabbed Installation Options: Refactored the 'Install Kmesh' section to use tabs, clearly separating instructions for 'Dual Engine (Default)' and 'Kernel Native' modes for improved readability and user experience.
  • Kernel-Native Specific Steps: Included specific steps for Kernel-Native mode, such as prerequisite checks for an Enhanced Kernel and instructions to modify values.yaml (via sed) or general Yaml configuration to enable kernel-native mode before installation.
  • Documentation Structure Improvement: Removed the standalone 'Change Kmesh Start Mode' section, as its content is now seamlessly integrated into the new tabbed installation guide, streamlining the documentation flow.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request does a great job of refactoring the installation documentation to include instructions for the Kernel-Native mode using tabs. The structure is much clearer now. I have a couple of suggestions to improve the clarity and portability of the commands in the new section to make the quick-start guide even more user-friendly.

1. Modify the startup mode to `kernel-native`:

```shell
sed -i 's/--mode=dual-engine/--mode=kernel-native/' deploy/charts/kmesh-helm/values.yaml

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The sed -i command is not portable and will fail on macOS, which uses BSD sed. To improve the user experience for developers on macOS, please add a note about the difference. For example, you could add a note above the code block mentioning that macOS users should use sed -i '' 's/--mode=dual-engine/--mode=kernel-native/' ....


### Option 2: Install from Yaml

1. Modify the startup mode in the Yaml configuration files (you may need to locate the specific DaemonSet configuration).

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This instruction is too vague for a quick-start guide. Users may not know which file to look for or what to change. Please provide more specific instructions, similar to the Helm installation section. It would be helpful to specify the exact file in deploy/yaml/ to modify and show an example of the change (e.g., using sed or a diff).

Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR enhances the quick-start documentation by adding a dedicated installation guide for Kernel-Native Mode alongside the existing Dual Engine mode instructions. The documentation now uses a tabbed interface to clearly separate the two installation modes.

Changes:

  • Refactored the "Install Kmesh" section to use Docusaurus Tabs/TabItem components
  • Added comprehensive Kernel-Native mode installation instructions with prerequisite warnings
  • Moved the previous "Change Kmesh Start Mode" section into the Kernel-Native tab as installation steps

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +151 to +152
1. Modify the startup mode in the Yaml configuration files (you may need to locate the specific DaemonSet configuration).

Copy link

Copilot AI Jan 11, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The instruction to modify the startup mode in Yaml configuration files is vague and unhelpful. Unlike the Helm option which provides a specific sed command, this option only mentions "you may need to locate the specific DaemonSet configuration" without providing concrete guidance on:

  1. Which file(s) to modify
  2. What the current value looks like
  3. What the new value should be
  4. The exact location within the file

Consider adding more specific instructions similar to the Helm option, or at least specify the file path and the parameter name to change.

Suggested change
1. Modify the startup mode in the Yaml configuration files (you may need to locate the specific DaemonSet configuration).
1. Open the Kmesh DaemonSet manifest under `deploy/yaml/` (for example, `deploy/yaml/kmesh-daemonset.yaml`) and update the startup mode:
- Locate the container `args` entry that contains `--mode=dual-engine`.
- Change it to `--mode=kernel-native`.
For example:
```yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kmesh-daemon
spec:
template:
spec:
containers:
- name: kmesh
args:
- "--mode=kernel-native"
```

Copilot uses AI. Check for mistakes.
time="2024-04-25T13:17:41Z" level=info msg="cni config file: /etc/cni/net.d/10-kindnet.conflist" subsys="cni installer"
time="2024-04-25T13:17:41Z" level=info msg="command Start cni successful" subsys=manager
```
### Option 1: Install from Helm (Recommended)
Copy link

Copilot AI Jan 11, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing an "Install from OCI Registry" option for the Kernel Native tab. While the Dual Engine tab provides this as Option 1 (Recommended), users following the Kernel Native instructions don't have an equivalent option explained. Consider adding instructions for how to install from the OCI registry with kernel-native mode, possibly using Helm's --set flag to override the mode parameter, or explicitly state that OCI registry installation is not recommended for kernel-native mode and explain why.

Copilot uses AI. Check for mistakes.
helm install kmesh ./deploy/charts/kmesh-helm -n kmesh-system --create-namespace
```

### Option 2: Install from Yaml
Copy link

Copilot AI Jan 11, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The "Install from Helm Chart Archive" option (Option 3) is missing from the Kernel Native tab. This creates an inconsistency with the Dual Engine tab which offers four installation options. Consider adding this option to maintain consistency, or explicitly state that not all installation methods are available for kernel-native mode.

Copilot uses AI. Check for mistakes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add Knernel-Native Mode install guide in quick-start

2 participants